Kubernetes Tools
A Kubernetes monitoring and diagnostics MCP server by Benedat LLC that provides strongly-typed tools for interacting with Kubernetes clusters without requiring kubectl knowledge. Built on the official Kubernetes Python API, it exposes read-only operations like listing pods, nodes, services, and deployments, retrieving container statuses and logs, and viewing pod events through both stdio and HTTP transports. The implementation emphasizes quality over quantity with comprehensive Pydantic models that mirror kubectl output formats, making it ideal for building AI agents that can perform cluster monitoring, root cause analysis, and troubleshooting workflows while maintaining type safety and detailed documentation for reliable agent interactions.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/benedatllc/k8stools
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Kubernetes Tools from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.